Filters








7,490 Hits in 7.6 sec

Splitting the structured paths in stratified graphs. Application in Natural Language Generation

Dana Dănciulescu, Mihaela Colhon
2014 Analele Stiintifice ale Universitatii Ovidius Constanta: Seria Matematica  
The generation method is based on labeled stratified graph representation and the inference mechanism is guided by the structured paths of these representations.  ...  In this manner we obtained a mechanism for generation coherent texts in a natural language (for this approach, Romanian).  ...  Starting from this method, in this paper we define a natural language generation mechanism based on labeled stratified graph representation and inference.  ... 
doi:10.2478/auom-2014-0031 fatcat:adi3bjjl4naivmss3qkeiz72t4

Access Control Policy Extraction from Unconstrained Natural Language Text

John Slankas, Laurie Williams
2013 2013 International Conference on Social Computing  
The goal of our research is to help developers improve security by extracting the access control policies implicitly and explicitly defined in natural language project artifacts.  ...  We propose a machine-learning based process to parse existing, unaltered natural language documents, such as requirement or technical specifications to extract the relevant subjects, actions, and resources  ...  ACKNOWLEDGMENT This work was supported by the U.S. Army Research Oƥce (ARO) under grant W911NF-08-1-0105 managed by NCSU Secure Open Systems Initiative (SOSI).  ... 
doi:10.1109/socialcom.2013.68 dblp:conf/socialcom/SlankasW13 fatcat:zfppr5ovm5darcq5lxeq2x5dba

Well-Stratified Linked Data for Well-Behaved Data Citation [article]

Dario De Nart and Dante Degl'Innocenti and Marco Peressotti
2019 arXiv   pre-print
Finally we suggest that data citation should be handled outside of the data, possibly with an ad-hoc language.  ...  In this paper we analyse the functional requirements of linked data citation and identify a minimal set of operations and primitives needed to realize such task.  ...  While there is a general agreement on the need for data citation to ensure research reproducibility and to facilitate data reuse, the research community is still debating how to concretely realise it.  ... 
arXiv:1512.02898v3 fatcat:f6j4vvbojbbsxil643xmy2srxu

Forthcoming papers

1998 Artificial Intelligence  
In this paper we describe the Remote Agent, a specific autonomous agent architecture based on the principles of model-based programming, on-board deduction and search, and goal-directed closedloop commanding  ...  The demonstration of the integrated system as an on-board controller for Deep Space One, NASA's first New Millennium mission, is scheduled for a period of a week in late 1998.  ...  This changes the nature of media-specific generation (e.g., language or graphics generation), which must take into account the multimedia context in which it occurs.  ... 
doi:10.1016/s0004-3702(98)90015-7 fatcat:wovog2kmgvcr7clo2c6gyj5qrm

COMETA: A Corpus for Medical Entity Linking in the Social Media [article]

Marco Basaldella, Fangyu Liu, Ehsan Shareghi, Nigel Collier
2020 arXiv   pre-print
Whilst there has been growing progress in Entity Linking (EL) for general language, existing datasets fail to address the complex nature of health terminology in layman's language.  ...  Through benchmark experiments on 20 EL baselines from string- to neural-based models we shed light on the ability of these systems to perform complex inference on entities and concepts under 2 challenging  ...  In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 55-65.  ... 
arXiv:2010.03295v2 fatcat:7zuoouy2erf3xaxjqx5aheiqsy

Partial Compilation of ASP Programs

BERNARDO CUTERI, CARMINE DODARO, FRANCESCO RICCA, PETER SCHÜLLER
2019 Theory and Practice of Logic Programming  
Results show that our compilation-based approach improves on the state of the art in various scenarios, including cases in which the input program is stratified or the grounding blow-up makes the evaluation  ...  State-of-the-art ASP systems are based on the traditional ground&solve approach and are general-purpose implementations, i.e., they are essentially built once for any kind of input program.  ...  agreement No 825619 (AI4EU).  ... 
doi:10.1017/s1471068419000231 fatcat:lyfcirees5akzb2awyb553jfju

Descartes: Generating Short Descriptions of Wikipedia Articles [article]

Marija Sakota, Maxime Peyrard, Robert West
2022 arXiv   pre-print
Such performances are made possible by integrating other signals naturally existing in Wikipedia: (i) articles about the same entity in different languages, (ii) existing short descriptions in other languages  ...  We introduce Descartes, a model that can generate descriptions performing on par with human editors.  ...  Amazon Mechanical Turk. In addition to the automated evaluation, we perform human evaluation on Amazon Mechanical Turk. We test our model in three languages: English, Romanian, and Hindi.  ... 
arXiv:2205.10012v1 fatcat:aom5eqqnxjbe7krd3iqlu4b7qy

Identifying and Explaining Discriminative Attributes

Armins Stepanjans, André Freitas
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Identifying what is at the center of the meaning of a word and what discriminates it from other words is a fundamental natural language inference task.  ...  A core contribution of the paper is a quantitative and qualitative comparative analysis of different types of data sources and Knowledge Bases in the construction of explainable and explicit WVMs: (i)  ...  Acknowledgments The authors would like to thank Viktor Schlegel for the initial supporting machine learning baselines (not included here) and related work discussions in the beginning of the project.  ... 
doi:10.18653/v1/d19-1440 dblp:conf/emnlp/StepanjansF19 fatcat:ipenseutafcxtfzl3hp4hza2ki

Using Shape Expressions (Shex) To Share Rdf Data Models And To Guide Curation With Rigorous Validation

Katherine Thornton, Harold Solbrig, Gregory S. Stupp, Jose Emilio Labra Gayo, Daniel Mietchen, Eric Prud'hommeaux, Andra Waagmeester
2018 Zenodo  
knowledge base, which is the linked database built and maintained by the Wikimedia Foundation as a sister project to Wikipedia.  ...  For instance, a Shape Expression could prescribe that subjects in a given RDF graph that fall into the shape "Paper" are expected to have a section called "Abstract", and any ShEx implementation can confirm  ...  Portions of this work were also supported in part by NIH grant U01 HG009450.  ... 
doi:10.5281/zenodo.1214520 fatcat:rzlfw2jc7bd6npjowunl2mvse4

Structured Knowledge Discovery from Massive Text Corpus [article]

Chenwei Zhang
2019 arXiv   pre-print
In particular, four problems are studied in this dissertation: Structured Intent Detection for Natural Language Understanding, Structure-aware Natural Language Modeling, Generative Structured Knowledge  ...  A large volume of natural language texts is being generated by users in various forms, such as search queries, documents, and social media posts.  ...  In particular, four problems are studied in this dissertation: Structured Intent Detection for Natural Language Understanding, Structure-aware Natural Language Modeling, Generative Structured Knowledge  ... 
arXiv:1908.01837v1 fatcat:j46srlxblfd35cd4z6jkl43iiu

Factors related to treatment intensity in Swiss primary care

André Busato, Pius Matter, Beat Künzi
2009 BMC Health Services Research  
Analyses stratified by language regions showed differences that emphasize the effect of the cantonal based (fragmented) governance of Swiss health care.  ...  Methods: The study was designed as a cross-sectional investigation, based on the complete claims data from all Swiss health care insurers for the year 2004, which covered information from 6087 primary  ...  Acknowledgements The study was funded by the Swiss Health Observatory within the project "Démo Médicale" and, by contractual agreement; the funding organization had no involvement in the preparation of  ... 
doi:10.1186/1472-6963-9-49 pmid:19296846 pmcid:PMC2664802 fatcat:t26c2tb23vg2bdu4jkry2rlwyy

Towards Learning Causal Representations of Technical Word Embeddings for Smart Troubleshooting

Alexandre Trilla, Nenad Mijatovic, Xavier Vilasis-Cardona
2022 International Journal of Prognostics and Health Management  
analysis ontology and a set of written records on Return On Experience.  ...  This work explores how the causality inference paradigm may be applied to troubleshoot the root causes of failures through language processing and Deep Learning.  ...  The contribution of Alexandre Trilla to this research was partially supported by the Government of Catalonia (Generalitat de Catalunya) Grant No. 2020 DI 54.  ... 
doi:10.36001/ijphm.2022.v13i2.3127 fatcat:r2s6hcvaqrb3znbwy3exv4mbuu

Querying RDF Data from a Graph Database Perspective [chapter]

Renzo Angles, Claudio Gutierrez
2005 Lecture Notes in Computer Science  
We concentrate on query languages, analyze current RDF trends, and propose the incorporation to RDF query languages of primitives which are not present today, based on the experience and techniques of  ...  From this point of view it is compared with other database models, particularly with graph database models, which are very close in motivations and use cases to RDF.  ...  In addition, a query language based on the previous ideas was proposed in [FG00] .  ... 
doi:10.1007/11431053_24 fatcat:gia7gzrs2jhjdlecw3vvexop6y

Modelling Smart Contracts with DatalogMTL

Markus Nissl, Emanuel Sallinger
2022 International Conference on Extending Database Technology  
Recent proposals focus on using logical languages for the specification and verification of such agreements.  ...  Smart contracts are programs that are stored in distributed ledgers (e.g., blockchains) and are usually written in procedural languages to encode agreements between parties.  ...  This work was supported by the Vienna Science and Technology Fund (WWTF) grant VRG18-013, and the "rAIson data" Royal Society grant of Prof. Georg Gottlob.  ... 
dblp:conf/edbt/NisslS22 fatcat:jsdg442nazbinbfdo7hbg6i4ji

Using Shape Expressions (ShEx) to Share RDF Data Models and to Guide Curation with Rigorous Validation [chapter]

Katherine Thornton, Harold Solbrig, Gregory S. Stupp, Jose Emilio Labra Gayo, Daniel Mietchen, Eric Prud'hommeaux, Andra Waagmeester
2019 Lecture Notes in Computer Science  
knowledge base, which is the linked database built and maintained by the Wikimedia Foundation as a sister project to Wikipedia.  ...  For instance, a Shape Expression could prescribe that subjects in a given RDF graph that fall into the shape "Paper" are expected to have a section called "Abstract", and any ShEx implementation can confirm  ...  Portions of this work were also supported in part by NIH grant U01 HG009450.  ... 
doi:10.1007/978-3-030-21348-0_39 fatcat:nek2hcbsnnh3xk555d4m2eapea
« Previous Showing results 1 — 15 out of 7,490 results